© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 8830
    Prev
    Next
    INDEX
    Explanations

    sections related to political discourse and government actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    551
    +0.15
    0.7%
    447
    +0.14
    0.6%
    139
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.15
    0.08
    139
    +0.14
    0.07
    706
    +0.12
    0.07
    Negative Logits
    aic
    -0.71
     Window
    -0.70
    omorphic
    -0.68
     consequential
    -0.65
    igo
    -0.62
    artisan
    -0.62
     Gothic
    -0.61
    emetery
    -0.61
    ORN
    -0.59
    RAW
    -0.58
    POSITIVE LOGITS
     took
    1.19
     knew
    1.17
     chose
    1.16
     withdrew
    1.15
     gave
    1.13
     went
    1.13
     flew
    1.12
     wore
    1.10
     came
    1.08
     enjoys
    1.08
    Activations Density 0.283%

    No Known Activations